© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76788
    Prev
    Next
    INDEX
    Explanations

    times and durations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on expressions of specific clock times (e.g., “about 4:45 pm”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    馒头
    -0.84
     morgens
    -0.82
    Breakfast
    -0.81
    knecht
    -0.81
    rophoresis
    -0.79
     veinte
    -0.76
     Morning
    -0.76
    Days
    -0.74
     ут
    -0.73
    addContainerGap
    -0.73
    POSITIVE LOGITS
     shortly
    1.15
    7
    0.90
     approximately
    0.88
    も良い
    0.86
     quarter
    0.86
    UEL
    0.85
    ערך
    0.84
     around
    0.84
    quarter
    0.83
    accia
    0.80
    Activations Density 0.029%

    No Known Activations